pytorch 模型 Syntax error in input! 是什么原因导致的？

jefferyzhang 发表于 2020-5-8 08:31
NPU Team回复：
该问题已经解决，下一个版本发布就可以用了。

您好，我也遇到了同样的问题，至于您这边说的该问题已解决，下一个版本就可以用，这里的下一个版本指的是具体哪个版本呢

jefferyzhang 发表于 2020-8-20 08:35
1.3.2以后的版本。
置顶帖有1.4.0preview，你先试试

/envs/toolkit140/lib/python3.6/site-packages/onnx_tf/common/__init__.py:87: UserWarning: FrontendHandler.get_outputs_names is deprecated. It will be removed in future release.. Use node.outputs instead.
  warnings.warn(message)
Alg_Proj/Recog_Proj/weights/tsm.pt ********************
WARNING: Token 'COMMENT' defined, but not used
WARNING: There is 1 unused token
Syntax error in input! LexToken(<,'<',4,141)
2020-08-20 16:53:48.857839: W tensorflow/core/common_runtime/gpu/gpu_device.cc:1663] Cannot dlopen some GPU libraries. Skipping registering GPU devices...
done
--> Building model
W Genreate input meta fail, please check model.
W External input meta file "/tmp/tmp5onizp4b/tsm_inputmeta.yml" is not exists.
Traceback (most recent call last):
  File "/root/home/gan/home/ganhaiyang/rk1808/rknn_toolkit/examples/pytorch/tsm/test.py", line 71, in <module>
    ret = rknn.build(do_quantization=True, dataset='./dataset.txt')
  File "/home/ghy/anaconda3/envs/toolkit140/lib/python3.6/site-packages/rknn/api/rknn.py", line 238, in build
    ret = self.rknn_base.build(do_quantization=do_quantization, dataset=dataset, pack_vdata=pre_compile, batch_size=rknn_batch_size)
  File "rknn/api/rknn_base.py", line 719, in rknn.api.rknn_base.RKNNBase.build
  File "rknn/api/rknn_base.py", line 2249, in rknn.api.rknn_base.RKNNBase._generate_inputmeta
IndexError: list index out of range
还是这个问题啊，我用的是/toolkit140，torch 1.2.0，请问这个什么原因呢